人工智能,从入门到放弃

这些天试着玩一下ai

Step1:Tensorflow1.15环境的安装和配置
    安装和配置TensorFlow(如果慢,pip换成TUNA的源)
    https://blog.csdn.net/weixin_40925977/article/details/107306079
    换成TUNA的源(换源记得把https改成http或者安装openssl)  
    https://mirrors4.tuna.tsinghua.edu.cn/help/anaconda/
    pip换成TUNA的源参见
    https://www.runoob.com/w3cnote/pip-cn-mirror.html  
    命令如下:

    pip3 config set global.index-url 'https://pypi.tuna.tsinghua.edu.cn/simple'
    pip3 config set install.trusted-host 'https://pypi.tuna.tsinghua.edu.cn'

     解决安装中的问题(Solving environment: failed with initial frozen solve. Retrying with flexible solve)
    https://blog.csdn.net/hhhhhhhhhhwwwwwwwwww/article/details/112726892
Step2:用Tensorflow实战例子
    用Tensorflow对MINST识别的训练和测试
    https://blog.csdn.net/qq_32674829/article/details/82867900
    用PyTorch对MINST识别的训练和测试
    https://blog.csdn.net/weixin_44751294/article/details/116240084
    MNIST数据集的简介
    https://yunyaniu.blog.csdn.net/article/details/79094752

    原始英文版本MNIST数据集的下载路径和介绍

    http://yann.lecun.com/exdb/mnist/
    Stanford现实生活中房屋门牌号的数据集
    http://ufldl.stanford.edu/housenumbers/
Step3:一些问题的解决
    import trace error问题的解决
    https://blog.csdn.net/weixin_45953051/article/details/126218041
    小括号和中括号运用不当导致的出错以及解决。
    https://blog.csdn.net/qq_41112170/article/details/124044453

下面是以上的阶段成果,就是copy了前面文章的例子,稍微改了一下(第一行的import和后面有个中括号改成小括号)能运行通过。

#-*- coding: utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("C:/tensorflow/MNIST_data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 25
batch_size = 100
display_step = 1

# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28*28=784
y = tf.placeholder(tf.float32, [None, 10]) # 0-9 digits recognition => 10 classes

# Set model weights
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# Construct model
pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

# Minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Fit training using batch data
            _, c = sess.run((optimizer, cost), feed_dict={x: batch_xs,y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", ' %04d ' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print ("Optimization Finished!")

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy for 3000 examples
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print ("Accuracy:", accuracy.eval({x: mnist.test.images[:3000], y: mnist.test.labels[:3000]}))

 


Step4:进阶实战
    使用最新版本的Tensorflow测试Mnist
    使用Stanford数据集测试
    对比测试CUDA对训练时间的改善
    不用anaconda配置环境
    Ubuntu下环境的安装和对比
    
Step5:PyTorch环境配置和安装

posted @ 2022-11-17 08:46  shinedream  阅读(54)  评论(3编辑  收藏  举报